© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25621
    Prev
    Next
    INDEX
    Explanations

    months and dates

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is primarily activated by standalone numeric tokens (i.e. numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Duc
    -1.14
    今日の
    -1.07
     of
    -1.05
    Mit
    -0.98
    Respiratory
    -0.97
    hdysval
    -0.97
    Сейчас
    -0.96
    Интер
    -0.96
     possibilidades
    -0.93
     Selv
    -0.93
    POSITIVE LOGITS
     January
    1.62
     June
    1.55
     April
    1.42
     July
    1.38
     October
    1.36
     our
    1.34
     previous
    1.30
     November
    1.29
     December
    1.28
     March
    1.27
    Activations Density 0.030%

    No Known Activations